add docs

Author: qinxuye

doc/source/getting_started/installation.rst

@@ -88,7 +88,9 @@ Currently, supported models include:
 - ``minicpm3-4b``
 - ``internlm3-instruct``
 - ``moonlight-16b-a3b-instruct``
+- ``qwenLong-l1``
 - ``qwen3``
+- ``minicpm4``
 .. vllm_end
 
 To install Xinference and vLLM::

doc/source/models/builtin/image/flux.1-kontext-dev.rst

@@ -0,0 +1,27 @@
+.. _models_builtin_flux.1-kontext-dev:
+
+==================
+FLUX.1-Kontext-dev
+==================
+
+- **Model Name:** FLUX.1-Kontext-dev
+- **Model Family:** stable_diffusion
+- **Abilities:** image2image
+- **Available ControlNet:** None
+
+Specifications
+^^^^^^^^^^^^^^
+
+- **Model ID:** black-forest-labs/FLUX.1-Kontext-dev
+- **GGUF Model ID**: bullerwins/FLUX.1-Kontext-dev-GGUF
+- **GGUF Quantizations**: BF16, Q2_K, Q3_K_S, Q4_K_M, Q4_K_S, Q4_K_S, Q5_K_M, Q5_K_S, Q5_K_S, Q6_K, Q8_0
+
+
+Execute the following command to launch the model::
+
+   xinference launch --model-name FLUX.1-Kontext-dev --model-type image
+
+
+For GGUF quantization, using below command:
+
+    xinference launch --model-name FLUX.1-Kontext-dev --model-type image --gguf_quantization ${gguf_quantization} --cpu_offload True

doc/source/models/builtin/image/index.rst

@@ -15,6 +15,8 @@ The following is a list of built-in image models in Xinference:
 
    flux.1-dev
 
+   flux.1-kontext-dev
+  
    flux.1-schnell
 
    got-ocr2_0

doc/source/models/builtin/llm/index.rst

@@ -491,6 +491,11 @@ The following is a list of built-in LLM in Xinference:
      - 40960
      - Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support
 
+   * - :ref:`qwenlong-l1 <models_llm_qwenlong-l1>`
+     - chat
+     - 32768
+     - QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
+
    * - :ref:`qwq-32b <models_llm_qwq-32b>`
      - chat, reasoning, tools
      - 131072
@@ -796,6 +801,8 @@ The following is a list of built-in LLM in Xinference:
 
    qwen3
 
+   qwenlong-l1
+  
    qwq-32b
 
    qwq-32b-preview

doc/source/models/builtin/llm/qwenlong-l1.rst

@@ -0,0 +1,47 @@
+.. _models_llm_qwenlong-l1:
+
+========================================
+qwenLong-l1
+========================================
+
+- **Context Length:** 32768
+- **Model Name:** qwenLong-l1
+- **Languages:** en, zh
+- **Abilities:** chat
+- **Description:** QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
+
+Specifications
+^^^^^^^^^^^^^^
+
+
+Model Spec 1 (pytorch, 32 Billion)
+++++++++++++++++++++++++++++++++++++++++
+
+- **Model Format:** pytorch
+- **Model Size (in billions):** 32
+- **Quantizations:** none
+- **Engines**: vLLM, Transformers
+- **Model ID:** Tongyi-Zhiwen/QwenLong-L1-32B
+- **Model Hubs**:  `Hugging Face <https://huggingface.co/Tongyi-Zhiwen/QwenLong-L1-32B>`__, `ModelScope <https://modelscope.cn/models/iic/QwenLong-L1-32B>`__
+
+Execute the following command to launch the model, remember to replace ``${quantization}`` with your
+chosen quantization method from the options listed above::
+
+   xinference launch --model-engine ${engine} --model-name qwenLong-l1 --size-in-billions 32 --model-format pytorch --quantization ${quantization}
+
+
+Model Spec 2 (awq, 32 Billion)
+++++++++++++++++++++++++++++++++++++++++
+
+- **Model Format:** awq
+- **Model Size (in billions):** 32
+- **Quantizations:** Int4
+- **Engines**: vLLM, Transformers
+- **Model ID:** Tongyi-Zhiwen/QwenLong-L1-32B-AWQ
+- **Model Hubs**:  `Hugging Face <https://huggingface.co/Tongyi-Zhiwen/QwenLong-L1-32B-AWQ>`__, `ModelScope <https://modelscope.cn/models/iic/QwenLong-L1-32B-AWQ>`__
+
+Execute the following command to launch the model, remember to replace ``${quantization}`` with your
+chosen quantization method from the options listed above::
+
+   xinference launch --model-engine ${engine} --model-name qwenLong-l1 --size-in-billions 32 --model-format awq --quantization ${quantization}
+

doc/source/user_guide/backends.rst

@@ -151,7 +151,9 @@ Currently, supported model includes:
 - ``minicpm3-4b``
 - ``internlm3-instruct``
 - ``moonlight-16b-a3b-instruct``
+- ``qwenLong-l1``
 - ``qwen3``
+- ``minicpm4``
 .. vllm_end
 
 .. _sglang_backend: